Highlights
- Pro
Stars
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font for IDE and terminal, fine-grained customization options. 带连字和控制台图标的圆角等宽字体,中英文宽度完美2:1,细粒度的自定义选项
A powerful tool for creating fine-tuning datasets for LLM
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
Python implementation of AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.
Curated list of datasets and tools for post-training.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen2.5, Llama4, InternLM3, GLM4, Mistral, Yi1.5, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3…
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Fully open reproduction of DeepSeek-R1
Get your documents ready for gen AI
Retrieval and Retrieval-augmented LLMs
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM!🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
reverse proxy, online proxy, 反向代理,免翻墙访问Youtube/twitter/Google, 支持github和telegram web登录(请注意不要通过不信任的代理进行登录)。支持DuckDuckGo AI Chat(可免费访问chatGPT3.5和Claude3)
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Convert Compute And Books Into Instruct-Tuning Datasets! Makes: QA, RP, Classifiers.
A simple, easy-to-hack GraphRAG implementation
Deploy high-performance AI models and inference pipelines on FastAPI with built-in batching, streaming and more.
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具,将PDF转换成Markdown和JSON格式。